# GPT Image 1 Mini

A cost-efficient image generation model from OpenAI, delivering fast image creation from text prompts at a lower price point than the full-size variant.

- **Model ID:** `openai/gpt-image-1-mini`
- **Type:** image
- **Providers:** openai
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** $2/1M input tokens, $8/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-image-1-mini

## Supported parameters

- **Parameters:** `aspectRatio`, `resolution`, `n`, `seed`
- **Operations:** `text-to-image`, `image-to-image`, `inpainting`
- **Input modalities:** `text`, `image`
- **Output modalities:** `image`
- **Aspect ratios:** `1:1`, `2:3`, `3:2`
- **Resolutions:** `1024x1024`, `1024x1536`, `1536x1024`
- **Durations:** Not reported
- **Frame rates:** Not reported
- **Maximum outputs per request:** 10
- **Maximum input images:** 1
- **Input image formats:** `png`, `jpeg`, `webp`, `gif`
- **Maximum input image size:** 50 MB

## Example

```ts
import { experimental_generateImage as generateImage } from 'ai';

const result = await generateImage({
  model: 'openai/gpt-image-1-mini',
  prompt: 'A red balloon on a wooden table.'
});
```

## About

GPT Image 1 Mini was released on October 6, 2025 as a compact variant of OpenAI's image generation model. It prioritizes generation speed and cost efficiency over maximum output quality, making it suitable for applications that produce images at high volume.

The model handles the same range of subjects and styles as its larger sibling but generates results faster and at lower cost per image. For many use cases, including thumbnails, content illustrations, rapid prototyping, and interactive creative tools, the quality is more than sufficient.

If you're building image-heavy applications, GPT Image 1 Mini makes per-request image generation practical at scale rather than reserving generation for premium features.

## What to consider

GPT Image 1 Mini generates images faster and more affordably than the full-size variant, making it practical for high-volume use cases where some quality tradeoff is acceptable.

For applications that generate many images per user session, the mini variant's economics make per-request generation viable.

## When to use

### Best For

- **High-volume image generation:** Applications producing many images per session at scale
- **Rapid prototyping:** Quick visual concept exploration during design workflows
- **Thumbnail generation:** Creating preview images and thumbnails at volume
- **Real-time creative tools:** Interactive image generation where speed matters
- **Content automation:** Batch image creation for content pipelines where the mini variant's speed and lower per-image cost matter more than peak fidelity

### Consider Alternatives When

- **Maximum quality:** Full gpt-image-1 for the highest fidelity output
- **Advanced generation:** gpt-image-1.5 for improved image generation quality
- **Image analysis:** GPT-4o or GPT-4.1 for understanding existing images
- **Text tasks:** Any GPT model handles text generation, analysis, or coding better than an image-generation model

## Best for

- **High-volume image generation:** Applications producing many images per session at scale
- **Rapid prototyping:** Quick visual concept exploration during design workflows
- **Thumbnail generation:** Creating preview images and thumbnails at volume
- **Real-time creative tools:** Interactive image generation where speed matters
- **Content automation:** Batch image creation for content pipelines where the mini variant's speed and lower per-image cost matter more than peak fidelity

## Consider alternatives

- **Maximum quality:** Full gpt-image-1 for the highest fidelity output
- **Advanced generation:** gpt-image-1.5 for improved image generation quality
- **Image analysis:** GPT-4o or GPT-4.1 for understanding existing images
- **Text tasks:** Any GPT model handles text generation, analysis, or coding better than an image-generation model

## Frequently asked questions

### How does GPT Image 1 Mini compare to gpt-image-1?

It generates images faster and more affordably, with some quality tradeoff. For many applications the difference is acceptable, especially at high volume.

### What can GPT Image 1 Mini generate?

The same range of subjects and styles as gpt-image-1, including photorealistic scenes, illustrations, and various artistic styles.

### Is GPT Image 1 Mini suitable for production use?

Yes. Its speed and pricing make it practical for production applications that generate images at volume.

### How does AI Gateway handle authentication for GPT Image 1 Mini?

AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.

### Can I edit existing images with GPT Image 1 Mini?

Check the API documentation for the specific editing capabilities available with the mini variant.

### What are typical generation times?

This page shows live performance metrics measured across real AI Gateway traffic.

## Links

- [Model page](https://vercel.com/ai-gateway/models/gpt-image-1-mini)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://platform.openai.com/docs/models/gpt-image-1-mini)
- [Provider pricing](https://platform.openai.com/docs/pricing#image-generation)